Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 358 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.6526. Min Act: -0.1700
Data Index: 1645338 (Python Code)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.6044. Min Act: -0.1700
Data Index: 1568687 (Python Code)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.5560. Min Act: -0.1700
Data Index: 1620825 (Python Code)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.5722. Min Act: -0.1700
Data Index: 1397773 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.5722. Min Act: -0.1700
Data Index: 866308 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.5399. Min Act: -0.1700
Data Index: 1530532 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.5237. Min Act: -0.1700
Data Index: 926311 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.5076. Min Act: -0.1699
Data Index: 1494118 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.5237. Min Act: -0.1700
Data Index: 1534265 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4914. Min Act: -0.1700
Data Index: 1387174 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4914. Min Act: -0.1700
Data Index: 378846 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4914. Min Act: -0.1700
Data Index: 781022 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4914. Min Act: -0.1700
Data Index: 1579925 (Python Code)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4752. Min Act: -0.1700
Data Index: 1117884 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4589. Min Act: -0.1700
Data Index: 1263720 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4752. Min Act: -0.1700
Data Index: 1329264 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4427. Min Act: -0.1700
Data Index: 603764 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4589. Min Act: -0.1700
Data Index: 1389666 (Python Code)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4589. Min Act: -0.1700
Data Index: 1430164 (Python Code)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6526. Min Range: -2.6526
Max Act: 2.4589. Min Act: -0.1700
Data Index: 1400406 (Python Code)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19